NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77TGS26SJPY8FRF02TB79D
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 40s
Cost:
$0.026829
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.08%
Matches word count
(details)
99.54%
Dialogue to Total Word Ratio
(details)
49.8114%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly adjusted her pink knitted balaclava while Bill checked a utility belt stocked exclusively with juice boxes. "Check the blueprints, Bill." "It's a crayon drawing, Molly. The treasure room is labeled 'Kitchen' with a smiley face." "Amateur hour. What's the guard rotation?" "Three toddlers on sugar crashes and a golden retriever named Mr. Wiggles who defects for bacon." "Acceptable risk. Disguises?" "I secured two clown suits. Big shoes, rainbow wigs, the works." "Bill, we're cat burglars, not circus rejects. I am not wearing a nose that honks." "It's tactical misdirection! Nobody suspects the juggling thief." "They suspect the juggling thief when he pockets the LEGO Death Star. What's the extraction route?" "We slip out during the musical chairs chaos. I've rigged the playlist to loop 'Baby Shark' for maximum distraction." "Diabolical. And the piƱata?" "Structural weak point. One whack with the foam bat and candy shrapnel covers our escape. We grab the gift bags and vanish." "Do you have the silent whacker?" "Squeaky hammer only. It's all I could find." "You're compromising the op, Bill. And the loot?" "All presents. Including the mystery box wrapped in dinosaurs." "That's my target. I heard it's a vintage Transformer." "Molly, that's for the birthday boy." "Not after we rappel down the chimney in oversized pants. Sync watches?" "My watch is a sticker of a rocket ship." "Perfect. Move out, you floppy-shoed maniac."
created_at
"2026-04-27T10:30:08.937Z"
4/27/2026, 10:30:08 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1111
moderation_latency
(null)
generation_time
100119
tokens_prompt
77
tokens_completion
3478
native_tokens_prompt
76
native_tokens_completion
3427
native_tokens_completion_images
(null)
native_tokens_reasoning
3063
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0268294
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-202efd08-187a-9fb2-90fb-3a6b7ba42a24"
is_byok
false
latency
1111
model_permaslug
"qwen/qwen3.6-max-preview-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777285808-ec791pJ8IISMwrHX3SUl"
session_id
(null)
api_type
"completions"
id
"gen-1777285808-cj9FW8KzoXgtt2qoe9Pj"
upstream_id
"chatcmpl-202efd08-187a-9fb2-90fb-3a6b7ba42a24"
total_cost
0.0268294
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.08%
Matches word count
n/a
neededClean
false
words
229
99.54%
Dialogue to Total Word Ratio
Ratio: 92.61%, Deviation: 2.61%
neededClean
false
wordsTotal
230
wordsDialogue
213
49.8114%